{"total":35,"rows":[{"id":"2102.09690","title":"Calibrate Before Use: Improving Few-Shot Performance of Language Models","created":"2021-02-19","cited_by_count":1392,"area":null},{"id":"2305.17926","title":"Large Language Models are not Fair Evaluators","created":"2023-05-29","cited_by_count":1085,"area":null},{"id":"2406.04127","title":"Are We Done with MMLU?","created":"2024-06-06","cited_by_count":194,"area":null},{"id":"2102.00086","title":"Challenges in Automated Debiasing for Toxic Language Detection","created":"2021-01-29","cited_by_count":96,"area":null},{"id":"2302.04156","title":"Prompting for Multimodal Hateful Meme Classification","created":"2023-02-08","cited_by_count":69,"area":null},{"id":"2203.12942","title":"Generating Data to Mitigate Spurious Correlations in Natural Language Inference Datasets","created":"2022-03-24","cited_by_count":54,"area":null},{"id":"2205.00415","title":"Don't Blame the Annotator: Bias Already Starts in the Annotation Instructions","created":"2022-05-01","cited_by_count":47,"area":null},{"id":"2109.00087","title":"It's not Rocket Science : Interpreting Figurative Language in Narratives","created":"2021-08-31","cited_by_count":39,"area":null},{"id":"2110.14375","title":"Perceptual Score: What Data Modalities Does Your Model Perceive?","created":"2021-10-27","cited_by_count":35,"area":null},{"id":"2112.09062","title":"Models in the Loop: Aiding Crowdworkers with Generative Annotation Assistants","created":"2021-12-16","cited_by_count":31,"area":null},{"id":"2203.12258","title":"Can Prompt Probe Pretrained Language Models? Understanding the Invisible Risks from a Causal View","created":"2022-03-23","cited_by_count":31,"area":null},{"id":"2102.12634","title":"Automatic Story Generation: Challenges and Attempts","created":"2021-02-25","cited_by_count":28,"area":null},{"id":"2305.09022","title":"It Takes Two to Tango: Navigating Conceptualizations of NLP Tasks and Measurements of Performance","created":"2023-05-15","cited_by_count":26,"area":null},{"id":"2108.12960","title":"LOT: A Story-Centric Benchmark for Evaluating Chinese Long Text Understanding and Generation","created":"2021-08-30","cited_by_count":24,"area":null},{"id":"2109.04144","title":"Avoiding Inference Heuristics in Few-shot Prompt-based Finetuning","created":"2021-09-09","cited_by_count":23,"area":null},{"id":"2109.04947","title":"Tiered Reasoning for Intuitive Physics: Toward Verifiable Commonsense Language Understanding","created":"2021-09-10","cited_by_count":19,"area":null},{"id":"2204.12708","title":"On the Limitations of Dataset Balancing: The Lost Battle Against Spurious Correlations","created":"2022-04-27","cited_by_count":19,"area":null},{"id":"2104.07064","title":"Is Everything in Order? A Simple Way to Order Sentences","created":"2021-04-14","cited_by_count":15,"area":null},{"id":"2108.12844","title":"Behind the Scenes: An Exploration of Trigger Biases Problem in Few-Shot Event Classification","created":"2021-08-29","cited_by_count":8,"area":null},{"id":"2109.04922","title":"Beyond the Tip of the Iceberg: Assessing Coherence of Text Classifiers","created":"2021-09-10","cited_by_count":5,"area":null},{"id":"2109.06807","title":"A Temporal Variational Model for Story Generation","created":"2021-09-14","cited_by_count":5,"area":null},{"id":"2305.18917","title":"Fighting Bias with Bias: Promoting Model Robustness by Amplifying Dataset Biases","created":"2023-05-30","cited_by_count":5,"area":null},{"id":"2312.13503","title":"InfoVisDial: An Informative Visual Dialogue Dataset by Bridging Large Multimodal and Language Models","created":"2023-12-21","cited_by_count":5,"area":null},{"id":"2403.02472","title":"OffensiveLang: A Community Based Implicit Offensive Language Dataset","created":"2024-03-04","cited_by_count":3,"area":null},{"id":"2203.06404","title":"A Proposal to Study \"Is High Quality Data All We Need?\"","created":"2022-03-12","cited_by_count":2,"area":null},{"id":"2110.11899","title":"Challenges in Procedural Multimodal Machine Comprehension:A Novel Way To Benchmark","created":"2021-10-22","cited_by_count":1,"area":null},{"id":"2210.07566","title":"A Survey of Parameters Associated with the Quality of Benchmarks in NLP","created":"2022-10-14","cited_by_count":1,"area":null},{"id":"2311.12373","title":"Beyond Turing: A Comparative Analysis of Approaches for Detecting Machine-Generated Text","created":"2023-11-21","cited_by_count":1,"area":null},{"id":"2410.03049","title":"Scalable Frame-based Construction of Sociocultural NormBases for Socially-Aware Dialogues","created":"2024-10-04","cited_by_count":1,"area":null},{"id":"2503.05047","title":"Biases in Large Language Model-Elicited Text: A Case Study in Natural Language Inference","created":"2025-03-06","cited_by_count":1,"area":null},{"id":"2604.12337","title":"Identifying and Mitigating Gender Cues in Academic Recommendation Letters: An Interpretability Case Study","created":"2026-04-14","cited_by_count":1,"area":null},{"id":"2104.09712","title":"Problems and Countermeasures in Natural Language Processing Evaluation","created":"2021-04-20","cited_by_count":0,"area":null},{"id":"2302.04434","title":"Real-Time Visual Feedback to Guide Benchmark Creation: A Human-and-Metric-in-the-Loop Workflow","created":"2023-02-09","cited_by_count":0,"area":null},{"id":"2304.06184","title":"LINGO : Visually Debiasing Natural Language Instructions to Support Task Diversity","created":"2023-04-12","cited_by_count":0,"area":null},{"id":"2410.08996","title":"Hypothesis-only Biases in Large Language Model-Elicited Natural Language Inference","created":"2024-10-11","cited_by_count":0,"area":null}],"next_cursor":null}